augustocsc commited on
Commit
5c9cc76
·
verified ·
1 Parent(s): d638166

GPT-2 medium infix - Academic Experiment (682K, r=16)

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +202 -0
  2. adapter_config.json +33 -0
  3. adapter_model.safetensors +3 -0
  4. checkpoint-7000/README.md +202 -0
  5. checkpoint-7000/adapter_config.json +33 -0
  6. checkpoint-7000/adapter_model.safetensors +3 -0
  7. checkpoint-7000/merges.txt +0 -0
  8. checkpoint-7000/optimizer.pt +3 -0
  9. checkpoint-7000/rng_state.pth +3 -0
  10. checkpoint-7000/scaler.pt +3 -0
  11. checkpoint-7000/scheduler.pt +3 -0
  12. checkpoint-7000/special_tokens_map.json +6 -0
  13. checkpoint-7000/tokenizer.json +0 -0
  14. checkpoint-7000/tokenizer_config.json +21 -0
  15. checkpoint-7000/trainer_state.json +652 -0
  16. checkpoint-7000/training_args.bin +3 -0
  17. checkpoint-7000/vocab.json +0 -0
  18. checkpoint-7500/README.md +202 -0
  19. checkpoint-7500/adapter_config.json +33 -0
  20. checkpoint-7500/adapter_model.safetensors +3 -0
  21. checkpoint-7500/merges.txt +0 -0
  22. checkpoint-7500/optimizer.pt +3 -0
  23. checkpoint-7500/rng_state.pth +3 -0
  24. checkpoint-7500/scaler.pt +3 -0
  25. checkpoint-7500/scheduler.pt +3 -0
  26. checkpoint-7500/special_tokens_map.json +6 -0
  27. checkpoint-7500/tokenizer.json +0 -0
  28. checkpoint-7500/tokenizer_config.json +21 -0
  29. checkpoint-7500/trainer_state.json +695 -0
  30. checkpoint-7500/training_args.bin +3 -0
  31. checkpoint-7500/vocab.json +0 -0
  32. checkpoint-8000/README.md +202 -0
  33. checkpoint-8000/adapter_config.json +33 -0
  34. checkpoint-8000/adapter_model.safetensors +3 -0
  35. checkpoint-8000/merges.txt +0 -0
  36. checkpoint-8000/optimizer.pt +3 -0
  37. checkpoint-8000/rng_state.pth +3 -0
  38. checkpoint-8000/scaler.pt +3 -0
  39. checkpoint-8000/scheduler.pt +3 -0
  40. checkpoint-8000/special_tokens_map.json +6 -0
  41. checkpoint-8000/tokenizer.json +0 -0
  42. checkpoint-8000/tokenizer_config.json +21 -0
  43. checkpoint-8000/trainer_state.json +738 -0
  44. checkpoint-8000/training_args.bin +3 -0
  45. checkpoint-8000/vocab.json +0 -0
  46. merges.txt +0 -0
  47. special_tokens_map.json +6 -0
  48. tokenizer.json +0 -0
  49. tokenizer_config.json +21 -0
  50. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: gpt2-medium
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.1
adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "gpt2-medium",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": true,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "c_attn"
28
+ ],
29
+ "task_type": "CAUSAL_LM",
30
+ "trainable_token_indices": null,
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03de0a9f40190e75e2b6373b4563320465f716ffcfaacf7da7d557849900ad9f
3
+ size 3151856
checkpoint-7000/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: gpt2-medium
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.1
checkpoint-7000/adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "gpt2-medium",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": true,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "c_attn"
28
+ ],
29
+ "task_type": "CAUSAL_LM",
30
+ "trainable_token_indices": null,
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
checkpoint-7000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19a42f37241ed08a568989d717fbcc3093fb1606f9fa1c97a1b1e82d6fe2a58c
3
+ size 3151856
checkpoint-7000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-7000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ca0a64771d4aefb626748dc00e48fd10e1a7b20647f9385562b7b05304aa54c
3
+ size 6332154
checkpoint-7000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7736eeb669f6553d3afec67f75e734734972e3a74d8013e4e06e661371850460
3
+ size 14244
checkpoint-7000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1649d3b3e023e1971bf1f99ed02274c67a4f14e5a2d48039bdea3dcc4713a9d
3
+ size 988
checkpoint-7000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4213e2b04896bb91a6c2489ed036d21f758cf285c8091b4910a06ba23f2dc2b4
3
+ size 1064
checkpoint-7000/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-7000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-7000/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
checkpoint-7000/trainer_state.json ADDED
@@ -0,0 +1,652 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 6500,
3
+ "best_metric": 0.2912672758102417,
4
+ "best_model_checkpoint": "./output/gpt2_medium_infix_682k/checkpoint-6500",
5
+ "epoch": 0.16411891587733282,
6
+ "eval_steps": 500,
7
+ "global_step": 7000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 2.3445559411047548e-05,
14
+ "grad_norm": 0.5072287321090698,
15
+ "learning_rate": 0.0,
16
+ "loss": 2.1103,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.002344555941104755,
21
+ "grad_norm": 0.6697903871536255,
22
+ "learning_rate": 5.940000000000001e-06,
23
+ "loss": 2.0556,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.00468911188220951,
28
+ "grad_norm": 0.824173092842102,
29
+ "learning_rate": 1.1940000000000001e-05,
30
+ "loss": 1.8837,
31
+ "step": 200
32
+ },
33
+ {
34
+ "epoch": 0.007033667823314264,
35
+ "grad_norm": 0.8375747203826904,
36
+ "learning_rate": 1.794e-05,
37
+ "loss": 1.3238,
38
+ "step": 300
39
+ },
40
+ {
41
+ "epoch": 0.00937822376441902,
42
+ "grad_norm": 0.6335204243659973,
43
+ "learning_rate": 2.394e-05,
44
+ "loss": 0.7333,
45
+ "step": 400
46
+ },
47
+ {
48
+ "epoch": 0.011722779705523774,
49
+ "grad_norm": 0.6748506426811218,
50
+ "learning_rate": 2.994e-05,
51
+ "loss": 0.502,
52
+ "step": 500
53
+ },
54
+ {
55
+ "epoch": 0.011722779705523774,
56
+ "eval_loss": 0.38173994421958923,
57
+ "eval_runtime": 553.6778,
58
+ "eval_samples_per_second": 136.95,
59
+ "eval_steps_per_second": 34.238,
60
+ "step": 500
61
+ },
62
+ {
63
+ "epoch": 0.014067335646628529,
64
+ "grad_norm": 0.683403730392456,
65
+ "learning_rate": 2.99766978408235e-05,
66
+ "loss": 0.4372,
67
+ "step": 600
68
+ },
69
+ {
70
+ "epoch": 0.016411891587733284,
71
+ "grad_norm": 0.6685835719108582,
72
+ "learning_rate": 2.995316030630178e-05,
73
+ "loss": 0.4075,
74
+ "step": 700
75
+ },
76
+ {
77
+ "epoch": 0.01875644752883804,
78
+ "grad_norm": 0.7494884729385376,
79
+ "learning_rate": 2.9929622771780066e-05,
80
+ "loss": 0.3886,
81
+ "step": 800
82
+ },
83
+ {
84
+ "epoch": 0.021101003469942793,
85
+ "grad_norm": 0.6221954226493835,
86
+ "learning_rate": 2.990608523725835e-05,
87
+ "loss": 0.387,
88
+ "step": 900
89
+ },
90
+ {
91
+ "epoch": 0.023445559411047548,
92
+ "grad_norm": 0.6262496709823608,
93
+ "learning_rate": 2.9882547702736632e-05,
94
+ "loss": 0.3679,
95
+ "step": 1000
96
+ },
97
+ {
98
+ "epoch": 0.023445559411047548,
99
+ "eval_loss": 0.33507269620895386,
100
+ "eval_runtime": 554.2605,
101
+ "eval_samples_per_second": 136.806,
102
+ "eval_steps_per_second": 34.202,
103
+ "step": 1000
104
+ },
105
+ {
106
+ "epoch": 0.025790115352152303,
107
+ "grad_norm": 0.6066267490386963,
108
+ "learning_rate": 2.9859010168214913e-05,
109
+ "loss": 0.3665,
110
+ "step": 1100
111
+ },
112
+ {
113
+ "epoch": 0.028134671293257058,
114
+ "grad_norm": 0.7456773519515991,
115
+ "learning_rate": 2.9835472633693198e-05,
116
+ "loss": 0.3602,
117
+ "step": 1200
118
+ },
119
+ {
120
+ "epoch": 0.030479227234361812,
121
+ "grad_norm": 0.6481399536132812,
122
+ "learning_rate": 2.981193509917148e-05,
123
+ "loss": 0.3511,
124
+ "step": 1300
125
+ },
126
+ {
127
+ "epoch": 0.03282378317546657,
128
+ "grad_norm": 0.6657889485359192,
129
+ "learning_rate": 2.9788397564649763e-05,
130
+ "loss": 0.348,
131
+ "step": 1400
132
+ },
133
+ {
134
+ "epoch": 0.03516833911657132,
135
+ "grad_norm": 0.6899926662445068,
136
+ "learning_rate": 2.9764860030128045e-05,
137
+ "loss": 0.3446,
138
+ "step": 1500
139
+ },
140
+ {
141
+ "epoch": 0.03516833911657132,
142
+ "eval_loss": 0.3230918049812317,
143
+ "eval_runtime": 559.4449,
144
+ "eval_samples_per_second": 135.538,
145
+ "eval_steps_per_second": 33.885,
146
+ "step": 1500
147
+ },
148
+ {
149
+ "epoch": 0.03751289505767608,
150
+ "grad_norm": 0.6252778172492981,
151
+ "learning_rate": 2.974132249560633e-05,
152
+ "loss": 0.341,
153
+ "step": 1600
154
+ },
155
+ {
156
+ "epoch": 0.03985745099878083,
157
+ "grad_norm": 0.5434716939926147,
158
+ "learning_rate": 2.971778496108461e-05,
159
+ "loss": 0.3385,
160
+ "step": 1700
161
+ },
162
+ {
163
+ "epoch": 0.042202006939885586,
164
+ "grad_norm": 0.5847312211990356,
165
+ "learning_rate": 2.969424742656289e-05,
166
+ "loss": 0.3388,
167
+ "step": 1800
168
+ },
169
+ {
170
+ "epoch": 0.04454656288099034,
171
+ "grad_norm": 0.6081641912460327,
172
+ "learning_rate": 2.9670709892041176e-05,
173
+ "loss": 0.3363,
174
+ "step": 1900
175
+ },
176
+ {
177
+ "epoch": 0.046891118822095096,
178
+ "grad_norm": 0.6961779594421387,
179
+ "learning_rate": 2.964717235751946e-05,
180
+ "loss": 0.3322,
181
+ "step": 2000
182
+ },
183
+ {
184
+ "epoch": 0.046891118822095096,
185
+ "eval_loss": 0.3134996294975281,
186
+ "eval_runtime": 560.4988,
187
+ "eval_samples_per_second": 135.283,
188
+ "eval_steps_per_second": 33.822,
189
+ "step": 2000
190
+ },
191
+ {
192
+ "epoch": 0.04923567476319985,
193
+ "grad_norm": 0.6722837090492249,
194
+ "learning_rate": 2.9623634822997742e-05,
195
+ "loss": 0.3356,
196
+ "step": 2100
197
+ },
198
+ {
199
+ "epoch": 0.051580230704304605,
200
+ "grad_norm": 0.6635189056396484,
201
+ "learning_rate": 2.9600097288476023e-05,
202
+ "loss": 0.3334,
203
+ "step": 2200
204
+ },
205
+ {
206
+ "epoch": 0.05392478664540936,
207
+ "grad_norm": 0.751340389251709,
208
+ "learning_rate": 2.9576559753954304e-05,
209
+ "loss": 0.3257,
210
+ "step": 2300
211
+ },
212
+ {
213
+ "epoch": 0.056269342586514115,
214
+ "grad_norm": 0.5838881134986877,
215
+ "learning_rate": 2.955302221943259e-05,
216
+ "loss": 0.3284,
217
+ "step": 2400
218
+ },
219
+ {
220
+ "epoch": 0.05861389852761887,
221
+ "grad_norm": 0.6517124772071838,
222
+ "learning_rate": 2.9529484684910874e-05,
223
+ "loss": 0.328,
224
+ "step": 2500
225
+ },
226
+ {
227
+ "epoch": 0.05861389852761887,
228
+ "eval_loss": 0.3083551824092865,
229
+ "eval_runtime": 561.306,
230
+ "eval_samples_per_second": 135.089,
231
+ "eval_steps_per_second": 33.773,
232
+ "step": 2500
233
+ },
234
+ {
235
+ "epoch": 0.060958454468723625,
236
+ "grad_norm": 0.5870581269264221,
237
+ "learning_rate": 2.9505947150389155e-05,
238
+ "loss": 0.3232,
239
+ "step": 2600
240
+ },
241
+ {
242
+ "epoch": 0.06330301040982837,
243
+ "grad_norm": 0.5278292298316956,
244
+ "learning_rate": 2.9482409615867436e-05,
245
+ "loss": 0.3241,
246
+ "step": 2700
247
+ },
248
+ {
249
+ "epoch": 0.06564756635093313,
250
+ "grad_norm": 0.7702547311782837,
251
+ "learning_rate": 2.945887208134572e-05,
252
+ "loss": 0.323,
253
+ "step": 2800
254
+ },
255
+ {
256
+ "epoch": 0.06799212229203788,
257
+ "grad_norm": 0.6794324517250061,
258
+ "learning_rate": 2.9435334546824002e-05,
259
+ "loss": 0.3218,
260
+ "step": 2900
261
+ },
262
+ {
263
+ "epoch": 0.07033667823314264,
264
+ "grad_norm": 0.798893392086029,
265
+ "learning_rate": 2.9411797012302287e-05,
266
+ "loss": 0.3247,
267
+ "step": 3000
268
+ },
269
+ {
270
+ "epoch": 0.07033667823314264,
271
+ "eval_loss": 0.30541837215423584,
272
+ "eval_runtime": 560.0773,
273
+ "eval_samples_per_second": 135.385,
274
+ "eval_steps_per_second": 33.847,
275
+ "step": 3000
276
+ },
277
+ {
278
+ "epoch": 0.07268123417424739,
279
+ "grad_norm": 0.680193305015564,
280
+ "learning_rate": 2.9388259477780568e-05,
281
+ "loss": 0.3229,
282
+ "step": 3100
283
+ },
284
+ {
285
+ "epoch": 0.07502579011535215,
286
+ "grad_norm": 0.5854464173316956,
287
+ "learning_rate": 2.9364721943258852e-05,
288
+ "loss": 0.3174,
289
+ "step": 3200
290
+ },
291
+ {
292
+ "epoch": 0.0773703460564569,
293
+ "grad_norm": 0.6867486238479614,
294
+ "learning_rate": 2.9341184408737134e-05,
295
+ "loss": 0.3141,
296
+ "step": 3300
297
+ },
298
+ {
299
+ "epoch": 0.07971490199756166,
300
+ "grad_norm": 0.5802149772644043,
301
+ "learning_rate": 2.9317646874215415e-05,
302
+ "loss": 0.3217,
303
+ "step": 3400
304
+ },
305
+ {
306
+ "epoch": 0.08205945793866641,
307
+ "grad_norm": 0.5844931602478027,
308
+ "learning_rate": 2.9294109339693696e-05,
309
+ "loss": 0.3203,
310
+ "step": 3500
311
+ },
312
+ {
313
+ "epoch": 0.08205945793866641,
314
+ "eval_loss": 0.30201342701911926,
315
+ "eval_runtime": 560.3182,
316
+ "eval_samples_per_second": 135.327,
317
+ "eval_steps_per_second": 33.833,
318
+ "step": 3500
319
+ },
320
+ {
321
+ "epoch": 0.08440401387977117,
322
+ "grad_norm": 0.6581853032112122,
323
+ "learning_rate": 2.9270571805171984e-05,
324
+ "loss": 0.3144,
325
+ "step": 3600
326
+ },
327
+ {
328
+ "epoch": 0.08674856982087592,
329
+ "grad_norm": 0.6662478446960449,
330
+ "learning_rate": 2.9247034270650265e-05,
331
+ "loss": 0.3146,
332
+ "step": 3700
333
+ },
334
+ {
335
+ "epoch": 0.08909312576198068,
336
+ "grad_norm": 0.7843517065048218,
337
+ "learning_rate": 2.9223496736128546e-05,
338
+ "loss": 0.3159,
339
+ "step": 3800
340
+ },
341
+ {
342
+ "epoch": 0.09143768170308543,
343
+ "grad_norm": 0.6684930920600891,
344
+ "learning_rate": 2.9199959201606828e-05,
345
+ "loss": 0.3136,
346
+ "step": 3900
347
+ },
348
+ {
349
+ "epoch": 0.09378223764419019,
350
+ "grad_norm": 0.51703941822052,
351
+ "learning_rate": 2.9176421667085112e-05,
352
+ "loss": 0.3133,
353
+ "step": 4000
354
+ },
355
+ {
356
+ "epoch": 0.09378223764419019,
357
+ "eval_loss": 0.2996933162212372,
358
+ "eval_runtime": 562.1924,
359
+ "eval_samples_per_second": 134.876,
360
+ "eval_steps_per_second": 33.72,
361
+ "step": 4000
362
+ },
363
+ {
364
+ "epoch": 0.09612679358529494,
365
+ "grad_norm": 0.7229161858558655,
366
+ "learning_rate": 2.9152884132563397e-05,
367
+ "loss": 0.3107,
368
+ "step": 4100
369
+ },
370
+ {
371
+ "epoch": 0.0984713495263997,
372
+ "grad_norm": 0.6924107074737549,
373
+ "learning_rate": 2.9129346598041678e-05,
374
+ "loss": 0.3131,
375
+ "step": 4200
376
+ },
377
+ {
378
+ "epoch": 0.10081590546750445,
379
+ "grad_norm": 0.7141218185424805,
380
+ "learning_rate": 2.910580906351996e-05,
381
+ "loss": 0.3144,
382
+ "step": 4300
383
+ },
384
+ {
385
+ "epoch": 0.10316046140860921,
386
+ "grad_norm": 0.6682331562042236,
387
+ "learning_rate": 2.9082271528998244e-05,
388
+ "loss": 0.3138,
389
+ "step": 4400
390
+ },
391
+ {
392
+ "epoch": 0.10550501734971396,
393
+ "grad_norm": 0.5962845683097839,
394
+ "learning_rate": 2.9058733994476525e-05,
395
+ "loss": 0.3104,
396
+ "step": 4500
397
+ },
398
+ {
399
+ "epoch": 0.10550501734971396,
400
+ "eval_loss": 0.29778608679771423,
401
+ "eval_runtime": 562.3478,
402
+ "eval_samples_per_second": 134.838,
403
+ "eval_steps_per_second": 33.71,
404
+ "step": 4500
405
+ },
406
+ {
407
+ "epoch": 0.10784957329081872,
408
+ "grad_norm": 0.6476929187774658,
409
+ "learning_rate": 2.903519645995481e-05,
410
+ "loss": 0.308,
411
+ "step": 4600
412
+ },
413
+ {
414
+ "epoch": 0.11019412923192347,
415
+ "grad_norm": 0.6191292405128479,
416
+ "learning_rate": 2.901165892543309e-05,
417
+ "loss": 0.3095,
418
+ "step": 4700
419
+ },
420
+ {
421
+ "epoch": 0.11253868517302823,
422
+ "grad_norm": 0.5744597911834717,
423
+ "learning_rate": 2.8988121390911375e-05,
424
+ "loss": 0.3077,
425
+ "step": 4800
426
+ },
427
+ {
428
+ "epoch": 0.11488324111413298,
429
+ "grad_norm": 0.7545962929725647,
430
+ "learning_rate": 2.8964583856389657e-05,
431
+ "loss": 0.3084,
432
+ "step": 4900
433
+ },
434
+ {
435
+ "epoch": 0.11722779705523774,
436
+ "grad_norm": 0.6554388999938965,
437
+ "learning_rate": 2.8941046321867938e-05,
438
+ "loss": 0.309,
439
+ "step": 5000
440
+ },
441
+ {
442
+ "epoch": 0.11722779705523774,
443
+ "eval_loss": 0.2962198555469513,
444
+ "eval_runtime": 561.1396,
445
+ "eval_samples_per_second": 135.129,
446
+ "eval_steps_per_second": 33.783,
447
+ "step": 5000
448
+ },
449
+ {
450
+ "epoch": 0.11957235299634249,
451
+ "grad_norm": 0.613491952419281,
452
+ "learning_rate": 2.891750878734622e-05,
453
+ "loss": 0.3057,
454
+ "step": 5100
455
+ },
456
+ {
457
+ "epoch": 0.12191690893744725,
458
+ "grad_norm": 0.5974335074424744,
459
+ "learning_rate": 2.8893971252824507e-05,
460
+ "loss": 0.3064,
461
+ "step": 5200
462
+ },
463
+ {
464
+ "epoch": 0.124261464878552,
465
+ "grad_norm": 0.6582714319229126,
466
+ "learning_rate": 2.887043371830279e-05,
467
+ "loss": 0.305,
468
+ "step": 5300
469
+ },
470
+ {
471
+ "epoch": 0.12660602081965674,
472
+ "grad_norm": 0.520508348941803,
473
+ "learning_rate": 2.884689618378107e-05,
474
+ "loss": 0.3023,
475
+ "step": 5400
476
+ },
477
+ {
478
+ "epoch": 0.12895057676076152,
479
+ "grad_norm": 0.6541963815689087,
480
+ "learning_rate": 2.882335864925935e-05,
481
+ "loss": 0.3086,
482
+ "step": 5500
483
+ },
484
+ {
485
+ "epoch": 0.12895057676076152,
486
+ "eval_loss": 0.2944982349872589,
487
+ "eval_runtime": 561.0929,
488
+ "eval_samples_per_second": 135.14,
489
+ "eval_steps_per_second": 33.786,
490
+ "step": 5500
491
+ },
492
+ {
493
+ "epoch": 0.13129513270186627,
494
+ "grad_norm": 0.6329942345619202,
495
+ "learning_rate": 2.8799821114737635e-05,
496
+ "loss": 0.3057,
497
+ "step": 5600
498
+ },
499
+ {
500
+ "epoch": 0.13363968864297102,
501
+ "grad_norm": 0.7279817461967468,
502
+ "learning_rate": 2.877628358021592e-05,
503
+ "loss": 0.3064,
504
+ "step": 5700
505
+ },
506
+ {
507
+ "epoch": 0.13598424458407576,
508
+ "grad_norm": 0.5646392107009888,
509
+ "learning_rate": 2.87527460456942e-05,
510
+ "loss": 0.3059,
511
+ "step": 5800
512
+ },
513
+ {
514
+ "epoch": 0.13832880052518054,
515
+ "grad_norm": 0.639140248298645,
516
+ "learning_rate": 2.8729208511172482e-05,
517
+ "loss": 0.3049,
518
+ "step": 5900
519
+ },
520
+ {
521
+ "epoch": 0.1406733564662853,
522
+ "grad_norm": 0.5572499632835388,
523
+ "learning_rate": 2.8705670976650767e-05,
524
+ "loss": 0.3066,
525
+ "step": 6000
526
+ },
527
+ {
528
+ "epoch": 0.1406733564662853,
529
+ "eval_loss": 0.29302480816841125,
530
+ "eval_runtime": 561.3497,
531
+ "eval_samples_per_second": 135.078,
532
+ "eval_steps_per_second": 33.77,
533
+ "step": 6000
534
+ },
535
+ {
536
+ "epoch": 0.14301791240739004,
537
+ "grad_norm": 0.6419617533683777,
538
+ "learning_rate": 2.8682133442129048e-05,
539
+ "loss": 0.3016,
540
+ "step": 6100
541
+ },
542
+ {
543
+ "epoch": 0.14536246834849478,
544
+ "grad_norm": 0.5800477862358093,
545
+ "learning_rate": 2.8658595907607333e-05,
546
+ "loss": 0.3022,
547
+ "step": 6200
548
+ },
549
+ {
550
+ "epoch": 0.14770702428959956,
551
+ "grad_norm": 0.5249703526496887,
552
+ "learning_rate": 2.8635058373085614e-05,
553
+ "loss": 0.3022,
554
+ "step": 6300
555
+ },
556
+ {
557
+ "epoch": 0.1500515802307043,
558
+ "grad_norm": 0.6495929956436157,
559
+ "learning_rate": 2.86115208385639e-05,
560
+ "loss": 0.3037,
561
+ "step": 6400
562
+ },
563
+ {
564
+ "epoch": 0.15239613617180905,
565
+ "grad_norm": 0.626995325088501,
566
+ "learning_rate": 2.858798330404218e-05,
567
+ "loss": 0.3033,
568
+ "step": 6500
569
+ },
570
+ {
571
+ "epoch": 0.15239613617180905,
572
+ "eval_loss": 0.2912672758102417,
573
+ "eval_runtime": 560.0877,
574
+ "eval_samples_per_second": 135.382,
575
+ "eval_steps_per_second": 33.846,
576
+ "step": 6500
577
+ },
578
+ {
579
+ "epoch": 0.1547406921129138,
580
+ "grad_norm": 0.6745596528053284,
581
+ "learning_rate": 2.856444576952046e-05,
582
+ "loss": 0.2999,
583
+ "step": 6600
584
+ },
585
+ {
586
+ "epoch": 0.15708524805401858,
587
+ "grad_norm": 0.6391417980194092,
588
+ "learning_rate": 2.8540908234998742e-05,
589
+ "loss": 0.3049,
590
+ "step": 6700
591
+ },
592
+ {
593
+ "epoch": 0.15942980399512333,
594
+ "grad_norm": 0.8039213418960571,
595
+ "learning_rate": 2.851737070047703e-05,
596
+ "loss": 0.3012,
597
+ "step": 6800
598
+ },
599
+ {
600
+ "epoch": 0.16177435993622807,
601
+ "grad_norm": 0.6973159909248352,
602
+ "learning_rate": 2.849383316595531e-05,
603
+ "loss": 0.3019,
604
+ "step": 6900
605
+ },
606
+ {
607
+ "epoch": 0.16411891587733282,
608
+ "grad_norm": 0.6347749829292297,
609
+ "learning_rate": 2.8470295631433593e-05,
610
+ "loss": 0.3022,
611
+ "step": 7000
612
+ },
613
+ {
614
+ "epoch": 0.16411891587733282,
615
+ "eval_loss": 0.29215002059936523,
616
+ "eval_runtime": 560.1099,
617
+ "eval_samples_per_second": 135.377,
618
+ "eval_steps_per_second": 33.845,
619
+ "step": 7000
620
+ }
621
+ ],
622
+ "logging_steps": 100,
623
+ "max_steps": 127956,
624
+ "num_input_tokens_seen": 0,
625
+ "num_train_epochs": 3,
626
+ "save_steps": 500,
627
+ "stateful_callbacks": {
628
+ "EarlyStoppingCallback": {
629
+ "args": {
630
+ "early_stopping_patience": 3,
631
+ "early_stopping_threshold": 0.001
632
+ },
633
+ "attributes": {
634
+ "early_stopping_patience_counter": 1
635
+ }
636
+ },
637
+ "TrainerControl": {
638
+ "args": {
639
+ "should_epoch_stop": false,
640
+ "should_evaluate": false,
641
+ "should_log": false,
642
+ "should_save": true,
643
+ "should_training_stop": false
644
+ },
645
+ "attributes": {}
646
+ }
647
+ },
648
+ "total_flos": 2.367185768620032e+16,
649
+ "train_batch_size": 4,
650
+ "trial_name": null,
651
+ "trial_params": null
652
+ }
checkpoint-7000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f4782bd16b2095bcd48ed561cca0b58ff457efc18a2d0171cfcd8019f2a410
3
+ size 5304
checkpoint-7000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-7500/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: gpt2-medium
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.1
checkpoint-7500/adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "gpt2-medium",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": true,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "c_attn"
28
+ ],
29
+ "task_type": "CAUSAL_LM",
30
+ "trainable_token_indices": null,
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
checkpoint-7500/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6da72c9e3b0747d39de67a84a0402b80be86bc545c297db26d2de88badb7d8bd
3
+ size 3151856
checkpoint-7500/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-7500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:261cf2762ab537c2a99425c9a688062a5391126f14ad297c71be96259c01f91e
3
+ size 6332154
checkpoint-7500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e970011aa1fe9c8a12777d8c32b0dfe3d0041331392224b6f4219558c4d874
3
+ size 14244
checkpoint-7500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74619b44a91be55cfad18cd64253abbff929e15e9d1131493111f152cb65508c
3
+ size 988
checkpoint-7500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07a21a7fdbb46f1f2b46d391c0cc9dccfb66fd6d0148974d539552ca237a0847
3
+ size 1064
checkpoint-7500/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-7500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-7500/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
checkpoint-7500/trainer_state.json ADDED
@@ -0,0 +1,695 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 7500,
3
+ "best_metric": 0.2912307679653168,
4
+ "best_model_checkpoint": "./output/gpt2_medium_infix_682k/checkpoint-7500",
5
+ "epoch": 0.17584169558285662,
6
+ "eval_steps": 500,
7
+ "global_step": 7500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 2.3445559411047548e-05,
14
+ "grad_norm": 0.5072287321090698,
15
+ "learning_rate": 0.0,
16
+ "loss": 2.1103,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.002344555941104755,
21
+ "grad_norm": 0.6697903871536255,
22
+ "learning_rate": 5.940000000000001e-06,
23
+ "loss": 2.0556,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.00468911188220951,
28
+ "grad_norm": 0.824173092842102,
29
+ "learning_rate": 1.1940000000000001e-05,
30
+ "loss": 1.8837,
31
+ "step": 200
32
+ },
33
+ {
34
+ "epoch": 0.007033667823314264,
35
+ "grad_norm": 0.8375747203826904,
36
+ "learning_rate": 1.794e-05,
37
+ "loss": 1.3238,
38
+ "step": 300
39
+ },
40
+ {
41
+ "epoch": 0.00937822376441902,
42
+ "grad_norm": 0.6335204243659973,
43
+ "learning_rate": 2.394e-05,
44
+ "loss": 0.7333,
45
+ "step": 400
46
+ },
47
+ {
48
+ "epoch": 0.011722779705523774,
49
+ "grad_norm": 0.6748506426811218,
50
+ "learning_rate": 2.994e-05,
51
+ "loss": 0.502,
52
+ "step": 500
53
+ },
54
+ {
55
+ "epoch": 0.011722779705523774,
56
+ "eval_loss": 0.38173994421958923,
57
+ "eval_runtime": 553.6778,
58
+ "eval_samples_per_second": 136.95,
59
+ "eval_steps_per_second": 34.238,
60
+ "step": 500
61
+ },
62
+ {
63
+ "epoch": 0.014067335646628529,
64
+ "grad_norm": 0.683403730392456,
65
+ "learning_rate": 2.99766978408235e-05,
66
+ "loss": 0.4372,
67
+ "step": 600
68
+ },
69
+ {
70
+ "epoch": 0.016411891587733284,
71
+ "grad_norm": 0.6685835719108582,
72
+ "learning_rate": 2.995316030630178e-05,
73
+ "loss": 0.4075,
74
+ "step": 700
75
+ },
76
+ {
77
+ "epoch": 0.01875644752883804,
78
+ "grad_norm": 0.7494884729385376,
79
+ "learning_rate": 2.9929622771780066e-05,
80
+ "loss": 0.3886,
81
+ "step": 800
82
+ },
83
+ {
84
+ "epoch": 0.021101003469942793,
85
+ "grad_norm": 0.6221954226493835,
86
+ "learning_rate": 2.990608523725835e-05,
87
+ "loss": 0.387,
88
+ "step": 900
89
+ },
90
+ {
91
+ "epoch": 0.023445559411047548,
92
+ "grad_norm": 0.6262496709823608,
93
+ "learning_rate": 2.9882547702736632e-05,
94
+ "loss": 0.3679,
95
+ "step": 1000
96
+ },
97
+ {
98
+ "epoch": 0.023445559411047548,
99
+ "eval_loss": 0.33507269620895386,
100
+ "eval_runtime": 554.2605,
101
+ "eval_samples_per_second": 136.806,
102
+ "eval_steps_per_second": 34.202,
103
+ "step": 1000
104
+ },
105
+ {
106
+ "epoch": 0.025790115352152303,
107
+ "grad_norm": 0.6066267490386963,
108
+ "learning_rate": 2.9859010168214913e-05,
109
+ "loss": 0.3665,
110
+ "step": 1100
111
+ },
112
+ {
113
+ "epoch": 0.028134671293257058,
114
+ "grad_norm": 0.7456773519515991,
115
+ "learning_rate": 2.9835472633693198e-05,
116
+ "loss": 0.3602,
117
+ "step": 1200
118
+ },
119
+ {
120
+ "epoch": 0.030479227234361812,
121
+ "grad_norm": 0.6481399536132812,
122
+ "learning_rate": 2.981193509917148e-05,
123
+ "loss": 0.3511,
124
+ "step": 1300
125
+ },
126
+ {
127
+ "epoch": 0.03282378317546657,
128
+ "grad_norm": 0.6657889485359192,
129
+ "learning_rate": 2.9788397564649763e-05,
130
+ "loss": 0.348,
131
+ "step": 1400
132
+ },
133
+ {
134
+ "epoch": 0.03516833911657132,
135
+ "grad_norm": 0.6899926662445068,
136
+ "learning_rate": 2.9764860030128045e-05,
137
+ "loss": 0.3446,
138
+ "step": 1500
139
+ },
140
+ {
141
+ "epoch": 0.03516833911657132,
142
+ "eval_loss": 0.3230918049812317,
143
+ "eval_runtime": 559.4449,
144
+ "eval_samples_per_second": 135.538,
145
+ "eval_steps_per_second": 33.885,
146
+ "step": 1500
147
+ },
148
+ {
149
+ "epoch": 0.03751289505767608,
150
+ "grad_norm": 0.6252778172492981,
151
+ "learning_rate": 2.974132249560633e-05,
152
+ "loss": 0.341,
153
+ "step": 1600
154
+ },
155
+ {
156
+ "epoch": 0.03985745099878083,
157
+ "grad_norm": 0.5434716939926147,
158
+ "learning_rate": 2.971778496108461e-05,
159
+ "loss": 0.3385,
160
+ "step": 1700
161
+ },
162
+ {
163
+ "epoch": 0.042202006939885586,
164
+ "grad_norm": 0.5847312211990356,
165
+ "learning_rate": 2.969424742656289e-05,
166
+ "loss": 0.3388,
167
+ "step": 1800
168
+ },
169
+ {
170
+ "epoch": 0.04454656288099034,
171
+ "grad_norm": 0.6081641912460327,
172
+ "learning_rate": 2.9670709892041176e-05,
173
+ "loss": 0.3363,
174
+ "step": 1900
175
+ },
176
+ {
177
+ "epoch": 0.046891118822095096,
178
+ "grad_norm": 0.6961779594421387,
179
+ "learning_rate": 2.964717235751946e-05,
180
+ "loss": 0.3322,
181
+ "step": 2000
182
+ },
183
+ {
184
+ "epoch": 0.046891118822095096,
185
+ "eval_loss": 0.3134996294975281,
186
+ "eval_runtime": 560.4988,
187
+ "eval_samples_per_second": 135.283,
188
+ "eval_steps_per_second": 33.822,
189
+ "step": 2000
190
+ },
191
+ {
192
+ "epoch": 0.04923567476319985,
193
+ "grad_norm": 0.6722837090492249,
194
+ "learning_rate": 2.9623634822997742e-05,
195
+ "loss": 0.3356,
196
+ "step": 2100
197
+ },
198
+ {
199
+ "epoch": 0.051580230704304605,
200
+ "grad_norm": 0.6635189056396484,
201
+ "learning_rate": 2.9600097288476023e-05,
202
+ "loss": 0.3334,
203
+ "step": 2200
204
+ },
205
+ {
206
+ "epoch": 0.05392478664540936,
207
+ "grad_norm": 0.751340389251709,
208
+ "learning_rate": 2.9576559753954304e-05,
209
+ "loss": 0.3257,
210
+ "step": 2300
211
+ },
212
+ {
213
+ "epoch": 0.056269342586514115,
214
+ "grad_norm": 0.5838881134986877,
215
+ "learning_rate": 2.955302221943259e-05,
216
+ "loss": 0.3284,
217
+ "step": 2400
218
+ },
219
+ {
220
+ "epoch": 0.05861389852761887,
221
+ "grad_norm": 0.6517124772071838,
222
+ "learning_rate": 2.9529484684910874e-05,
223
+ "loss": 0.328,
224
+ "step": 2500
225
+ },
226
+ {
227
+ "epoch": 0.05861389852761887,
228
+ "eval_loss": 0.3083551824092865,
229
+ "eval_runtime": 561.306,
230
+ "eval_samples_per_second": 135.089,
231
+ "eval_steps_per_second": 33.773,
232
+ "step": 2500
233
+ },
234
+ {
235
+ "epoch": 0.060958454468723625,
236
+ "grad_norm": 0.5870581269264221,
237
+ "learning_rate": 2.9505947150389155e-05,
238
+ "loss": 0.3232,
239
+ "step": 2600
240
+ },
241
+ {
242
+ "epoch": 0.06330301040982837,
243
+ "grad_norm": 0.5278292298316956,
244
+ "learning_rate": 2.9482409615867436e-05,
245
+ "loss": 0.3241,
246
+ "step": 2700
247
+ },
248
+ {
249
+ "epoch": 0.06564756635093313,
250
+ "grad_norm": 0.7702547311782837,
251
+ "learning_rate": 2.945887208134572e-05,
252
+ "loss": 0.323,
253
+ "step": 2800
254
+ },
255
+ {
256
+ "epoch": 0.06799212229203788,
257
+ "grad_norm": 0.6794324517250061,
258
+ "learning_rate": 2.9435334546824002e-05,
259
+ "loss": 0.3218,
260
+ "step": 2900
261
+ },
262
+ {
263
+ "epoch": 0.07033667823314264,
264
+ "grad_norm": 0.798893392086029,
265
+ "learning_rate": 2.9411797012302287e-05,
266
+ "loss": 0.3247,
267
+ "step": 3000
268
+ },
269
+ {
270
+ "epoch": 0.07033667823314264,
271
+ "eval_loss": 0.30541837215423584,
272
+ "eval_runtime": 560.0773,
273
+ "eval_samples_per_second": 135.385,
274
+ "eval_steps_per_second": 33.847,
275
+ "step": 3000
276
+ },
277
+ {
278
+ "epoch": 0.07268123417424739,
279
+ "grad_norm": 0.680193305015564,
280
+ "learning_rate": 2.9388259477780568e-05,
281
+ "loss": 0.3229,
282
+ "step": 3100
283
+ },
284
+ {
285
+ "epoch": 0.07502579011535215,
286
+ "grad_norm": 0.5854464173316956,
287
+ "learning_rate": 2.9364721943258852e-05,
288
+ "loss": 0.3174,
289
+ "step": 3200
290
+ },
291
+ {
292
+ "epoch": 0.0773703460564569,
293
+ "grad_norm": 0.6867486238479614,
294
+ "learning_rate": 2.9341184408737134e-05,
295
+ "loss": 0.3141,
296
+ "step": 3300
297
+ },
298
+ {
299
+ "epoch": 0.07971490199756166,
300
+ "grad_norm": 0.5802149772644043,
301
+ "learning_rate": 2.9317646874215415e-05,
302
+ "loss": 0.3217,
303
+ "step": 3400
304
+ },
305
+ {
306
+ "epoch": 0.08205945793866641,
307
+ "grad_norm": 0.5844931602478027,
308
+ "learning_rate": 2.9294109339693696e-05,
309
+ "loss": 0.3203,
310
+ "step": 3500
311
+ },
312
+ {
313
+ "epoch": 0.08205945793866641,
314
+ "eval_loss": 0.30201342701911926,
315
+ "eval_runtime": 560.3182,
316
+ "eval_samples_per_second": 135.327,
317
+ "eval_steps_per_second": 33.833,
318
+ "step": 3500
319
+ },
320
+ {
321
+ "epoch": 0.08440401387977117,
322
+ "grad_norm": 0.6581853032112122,
323
+ "learning_rate": 2.9270571805171984e-05,
324
+ "loss": 0.3144,
325
+ "step": 3600
326
+ },
327
+ {
328
+ "epoch": 0.08674856982087592,
329
+ "grad_norm": 0.6662478446960449,
330
+ "learning_rate": 2.9247034270650265e-05,
331
+ "loss": 0.3146,
332
+ "step": 3700
333
+ },
334
+ {
335
+ "epoch": 0.08909312576198068,
336
+ "grad_norm": 0.7843517065048218,
337
+ "learning_rate": 2.9223496736128546e-05,
338
+ "loss": 0.3159,
339
+ "step": 3800
340
+ },
341
+ {
342
+ "epoch": 0.09143768170308543,
343
+ "grad_norm": 0.6684930920600891,
344
+ "learning_rate": 2.9199959201606828e-05,
345
+ "loss": 0.3136,
346
+ "step": 3900
347
+ },
348
+ {
349
+ "epoch": 0.09378223764419019,
350
+ "grad_norm": 0.51703941822052,
351
+ "learning_rate": 2.9176421667085112e-05,
352
+ "loss": 0.3133,
353
+ "step": 4000
354
+ },
355
+ {
356
+ "epoch": 0.09378223764419019,
357
+ "eval_loss": 0.2996933162212372,
358
+ "eval_runtime": 562.1924,
359
+ "eval_samples_per_second": 134.876,
360
+ "eval_steps_per_second": 33.72,
361
+ "step": 4000
362
+ },
363
+ {
364
+ "epoch": 0.09612679358529494,
365
+ "grad_norm": 0.7229161858558655,
366
+ "learning_rate": 2.9152884132563397e-05,
367
+ "loss": 0.3107,
368
+ "step": 4100
369
+ },
370
+ {
371
+ "epoch": 0.0984713495263997,
372
+ "grad_norm": 0.6924107074737549,
373
+ "learning_rate": 2.9129346598041678e-05,
374
+ "loss": 0.3131,
375
+ "step": 4200
376
+ },
377
+ {
378
+ "epoch": 0.10081590546750445,
379
+ "grad_norm": 0.7141218185424805,
380
+ "learning_rate": 2.910580906351996e-05,
381
+ "loss": 0.3144,
382
+ "step": 4300
383
+ },
384
+ {
385
+ "epoch": 0.10316046140860921,
386
+ "grad_norm": 0.6682331562042236,
387
+ "learning_rate": 2.9082271528998244e-05,
388
+ "loss": 0.3138,
389
+ "step": 4400
390
+ },
391
+ {
392
+ "epoch": 0.10550501734971396,
393
+ "grad_norm": 0.5962845683097839,
394
+ "learning_rate": 2.9058733994476525e-05,
395
+ "loss": 0.3104,
396
+ "step": 4500
397
+ },
398
+ {
399
+ "epoch": 0.10550501734971396,
400
+ "eval_loss": 0.29778608679771423,
401
+ "eval_runtime": 562.3478,
402
+ "eval_samples_per_second": 134.838,
403
+ "eval_steps_per_second": 33.71,
404
+ "step": 4500
405
+ },
406
+ {
407
+ "epoch": 0.10784957329081872,
408
+ "grad_norm": 0.6476929187774658,
409
+ "learning_rate": 2.903519645995481e-05,
410
+ "loss": 0.308,
411
+ "step": 4600
412
+ },
413
+ {
414
+ "epoch": 0.11019412923192347,
415
+ "grad_norm": 0.6191292405128479,
416
+ "learning_rate": 2.901165892543309e-05,
417
+ "loss": 0.3095,
418
+ "step": 4700
419
+ },
420
+ {
421
+ "epoch": 0.11253868517302823,
422
+ "grad_norm": 0.5744597911834717,
423
+ "learning_rate": 2.8988121390911375e-05,
424
+ "loss": 0.3077,
425
+ "step": 4800
426
+ },
427
+ {
428
+ "epoch": 0.11488324111413298,
429
+ "grad_norm": 0.7545962929725647,
430
+ "learning_rate": 2.8964583856389657e-05,
431
+ "loss": 0.3084,
432
+ "step": 4900
433
+ },
434
+ {
435
+ "epoch": 0.11722779705523774,
436
+ "grad_norm": 0.6554388999938965,
437
+ "learning_rate": 2.8941046321867938e-05,
438
+ "loss": 0.309,
439
+ "step": 5000
440
+ },
441
+ {
442
+ "epoch": 0.11722779705523774,
443
+ "eval_loss": 0.2962198555469513,
444
+ "eval_runtime": 561.1396,
445
+ "eval_samples_per_second": 135.129,
446
+ "eval_steps_per_second": 33.783,
447
+ "step": 5000
448
+ },
449
+ {
450
+ "epoch": 0.11957235299634249,
451
+ "grad_norm": 0.613491952419281,
452
+ "learning_rate": 2.891750878734622e-05,
453
+ "loss": 0.3057,
454
+ "step": 5100
455
+ },
456
+ {
457
+ "epoch": 0.12191690893744725,
458
+ "grad_norm": 0.5974335074424744,
459
+ "learning_rate": 2.8893971252824507e-05,
460
+ "loss": 0.3064,
461
+ "step": 5200
462
+ },
463
+ {
464
+ "epoch": 0.124261464878552,
465
+ "grad_norm": 0.6582714319229126,
466
+ "learning_rate": 2.887043371830279e-05,
467
+ "loss": 0.305,
468
+ "step": 5300
469
+ },
470
+ {
471
+ "epoch": 0.12660602081965674,
472
+ "grad_norm": 0.520508348941803,
473
+ "learning_rate": 2.884689618378107e-05,
474
+ "loss": 0.3023,
475
+ "step": 5400
476
+ },
477
+ {
478
+ "epoch": 0.12895057676076152,
479
+ "grad_norm": 0.6541963815689087,
480
+ "learning_rate": 2.882335864925935e-05,
481
+ "loss": 0.3086,
482
+ "step": 5500
483
+ },
484
+ {
485
+ "epoch": 0.12895057676076152,
486
+ "eval_loss": 0.2944982349872589,
487
+ "eval_runtime": 561.0929,
488
+ "eval_samples_per_second": 135.14,
489
+ "eval_steps_per_second": 33.786,
490
+ "step": 5500
491
+ },
492
+ {
493
+ "epoch": 0.13129513270186627,
494
+ "grad_norm": 0.6329942345619202,
495
+ "learning_rate": 2.8799821114737635e-05,
496
+ "loss": 0.3057,
497
+ "step": 5600
498
+ },
499
+ {
500
+ "epoch": 0.13363968864297102,
501
+ "grad_norm": 0.7279817461967468,
502
+ "learning_rate": 2.877628358021592e-05,
503
+ "loss": 0.3064,
504
+ "step": 5700
505
+ },
506
+ {
507
+ "epoch": 0.13598424458407576,
508
+ "grad_norm": 0.5646392107009888,
509
+ "learning_rate": 2.87527460456942e-05,
510
+ "loss": 0.3059,
511
+ "step": 5800
512
+ },
513
+ {
514
+ "epoch": 0.13832880052518054,
515
+ "grad_norm": 0.639140248298645,
516
+ "learning_rate": 2.8729208511172482e-05,
517
+ "loss": 0.3049,
518
+ "step": 5900
519
+ },
520
+ {
521
+ "epoch": 0.1406733564662853,
522
+ "grad_norm": 0.5572499632835388,
523
+ "learning_rate": 2.8705670976650767e-05,
524
+ "loss": 0.3066,
525
+ "step": 6000
526
+ },
527
+ {
528
+ "epoch": 0.1406733564662853,
529
+ "eval_loss": 0.29302480816841125,
530
+ "eval_runtime": 561.3497,
531
+ "eval_samples_per_second": 135.078,
532
+ "eval_steps_per_second": 33.77,
533
+ "step": 6000
534
+ },
535
+ {
536
+ "epoch": 0.14301791240739004,
537
+ "grad_norm": 0.6419617533683777,
538
+ "learning_rate": 2.8682133442129048e-05,
539
+ "loss": 0.3016,
540
+ "step": 6100
541
+ },
542
+ {
543
+ "epoch": 0.14536246834849478,
544
+ "grad_norm": 0.5800477862358093,
545
+ "learning_rate": 2.8658595907607333e-05,
546
+ "loss": 0.3022,
547
+ "step": 6200
548
+ },
549
+ {
550
+ "epoch": 0.14770702428959956,
551
+ "grad_norm": 0.5249703526496887,
552
+ "learning_rate": 2.8635058373085614e-05,
553
+ "loss": 0.3022,
554
+ "step": 6300
555
+ },
556
+ {
557
+ "epoch": 0.1500515802307043,
558
+ "grad_norm": 0.6495929956436157,
559
+ "learning_rate": 2.86115208385639e-05,
560
+ "loss": 0.3037,
561
+ "step": 6400
562
+ },
563
+ {
564
+ "epoch": 0.15239613617180905,
565
+ "grad_norm": 0.626995325088501,
566
+ "learning_rate": 2.858798330404218e-05,
567
+ "loss": 0.3033,
568
+ "step": 6500
569
+ },
570
+ {
571
+ "epoch": 0.15239613617180905,
572
+ "eval_loss": 0.2912672758102417,
573
+ "eval_runtime": 560.0877,
574
+ "eval_samples_per_second": 135.382,
575
+ "eval_steps_per_second": 33.846,
576
+ "step": 6500
577
+ },
578
+ {
579
+ "epoch": 0.1547406921129138,
580
+ "grad_norm": 0.6745596528053284,
581
+ "learning_rate": 2.856444576952046e-05,
582
+ "loss": 0.2999,
583
+ "step": 6600
584
+ },
585
+ {
586
+ "epoch": 0.15708524805401858,
587
+ "grad_norm": 0.6391417980194092,
588
+ "learning_rate": 2.8540908234998742e-05,
589
+ "loss": 0.3049,
590
+ "step": 6700
591
+ },
592
+ {
593
+ "epoch": 0.15942980399512333,
594
+ "grad_norm": 0.8039213418960571,
595
+ "learning_rate": 2.851737070047703e-05,
596
+ "loss": 0.3012,
597
+ "step": 6800
598
+ },
599
+ {
600
+ "epoch": 0.16177435993622807,
601
+ "grad_norm": 0.6973159909248352,
602
+ "learning_rate": 2.849383316595531e-05,
603
+ "loss": 0.3019,
604
+ "step": 6900
605
+ },
606
+ {
607
+ "epoch": 0.16411891587733282,
608
+ "grad_norm": 0.6347749829292297,
609
+ "learning_rate": 2.8470295631433593e-05,
610
+ "loss": 0.3022,
611
+ "step": 7000
612
+ },
613
+ {
614
+ "epoch": 0.16411891587733282,
615
+ "eval_loss": 0.29215002059936523,
616
+ "eval_runtime": 560.1099,
617
+ "eval_samples_per_second": 135.377,
618
+ "eval_steps_per_second": 33.845,
619
+ "step": 7000
620
+ },
621
+ {
622
+ "epoch": 0.1664634718184376,
623
+ "grad_norm": 0.6030504703521729,
624
+ "learning_rate": 2.8446758096911874e-05,
625
+ "loss": 0.3045,
626
+ "step": 7100
627
+ },
628
+ {
629
+ "epoch": 0.16880802775954235,
630
+ "grad_norm": 0.7266963124275208,
631
+ "learning_rate": 2.842322056239016e-05,
632
+ "loss": 0.299,
633
+ "step": 7200
634
+ },
635
+ {
636
+ "epoch": 0.1711525837006471,
637
+ "grad_norm": 0.5945442914962769,
638
+ "learning_rate": 2.8399683027868443e-05,
639
+ "loss": 0.2994,
640
+ "step": 7300
641
+ },
642
+ {
643
+ "epoch": 0.17349713964175184,
644
+ "grad_norm": 0.8690565228462219,
645
+ "learning_rate": 2.8376145493346724e-05,
646
+ "loss": 0.3036,
647
+ "step": 7400
648
+ },
649
+ {
650
+ "epoch": 0.17584169558285662,
651
+ "grad_norm": 0.6460816264152527,
652
+ "learning_rate": 2.8352607958825006e-05,
653
+ "loss": 0.2988,
654
+ "step": 7500
655
+ },
656
+ {
657
+ "epoch": 0.17584169558285662,
658
+ "eval_loss": 0.2912307679653168,
659
+ "eval_runtime": 561.9772,
660
+ "eval_samples_per_second": 134.927,
661
+ "eval_steps_per_second": 33.733,
662
+ "step": 7500
663
+ }
664
+ ],
665
+ "logging_steps": 100,
666
+ "max_steps": 127956,
667
+ "num_input_tokens_seen": 0,
668
+ "num_train_epochs": 3,
669
+ "save_steps": 500,
670
+ "stateful_callbacks": {
671
+ "EarlyStoppingCallback": {
672
+ "args": {
673
+ "early_stopping_patience": 3,
674
+ "early_stopping_threshold": 0.001
675
+ },
676
+ "attributes": {
677
+ "early_stopping_patience_counter": 2
678
+ }
679
+ },
680
+ "TrainerControl": {
681
+ "args": {
682
+ "should_epoch_stop": false,
683
+ "should_evaluate": false,
684
+ "should_log": false,
685
+ "should_save": true,
686
+ "should_training_stop": false
687
+ },
688
+ "attributes": {}
689
+ }
690
+ },
691
+ "total_flos": 2.5360314001096704e+16,
692
+ "train_batch_size": 4,
693
+ "trial_name": null,
694
+ "trial_params": null
695
+ }
checkpoint-7500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f4782bd16b2095bcd48ed561cca0b58ff457efc18a2d0171cfcd8019f2a410
3
+ size 5304
checkpoint-7500/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8000/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: gpt2-medium
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.1
checkpoint-8000/adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "gpt2-medium",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": true,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "c_attn"
28
+ ],
29
+ "task_type": "CAUSAL_LM",
30
+ "trainable_token_indices": null,
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
checkpoint-8000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03de0a9f40190e75e2b6373b4563320465f716ffcfaacf7da7d557849900ad9f
3
+ size 3151856
checkpoint-8000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cea7bf5c70ee58b3e5ee1e4884a8c7ba915607ab0d8ef4b235e45a72a0a4abf
3
+ size 6332154
checkpoint-8000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f63a41654a5fb8770e53664a99f0ec34caef6d82dca6a5c9df01f198a82c776
3
+ size 14244
checkpoint-8000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:277aa13cb2ec6fbc8e4950a74aadb07696752963130be9aa03b65700e040b1b0
3
+ size 988
checkpoint-8000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3a95f98fa1c5d9b432828698d0fd1ee6200a54e6d090b783157fe823afe71b1
3
+ size 1064
checkpoint-8000/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-8000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8000/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
checkpoint-8000/trainer_state.json ADDED
@@ -0,0 +1,738 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 8000,
3
+ "best_metric": 0.29071754217147827,
4
+ "best_model_checkpoint": "./output/gpt2_medium_infix_682k/checkpoint-8000",
5
+ "epoch": 0.18756447528838038,
6
+ "eval_steps": 500,
7
+ "global_step": 8000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 2.3445559411047548e-05,
14
+ "grad_norm": 0.5072287321090698,
15
+ "learning_rate": 0.0,
16
+ "loss": 2.1103,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.002344555941104755,
21
+ "grad_norm": 0.6697903871536255,
22
+ "learning_rate": 5.940000000000001e-06,
23
+ "loss": 2.0556,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.00468911188220951,
28
+ "grad_norm": 0.824173092842102,
29
+ "learning_rate": 1.1940000000000001e-05,
30
+ "loss": 1.8837,
31
+ "step": 200
32
+ },
33
+ {
34
+ "epoch": 0.007033667823314264,
35
+ "grad_norm": 0.8375747203826904,
36
+ "learning_rate": 1.794e-05,
37
+ "loss": 1.3238,
38
+ "step": 300
39
+ },
40
+ {
41
+ "epoch": 0.00937822376441902,
42
+ "grad_norm": 0.6335204243659973,
43
+ "learning_rate": 2.394e-05,
44
+ "loss": 0.7333,
45
+ "step": 400
46
+ },
47
+ {
48
+ "epoch": 0.011722779705523774,
49
+ "grad_norm": 0.6748506426811218,
50
+ "learning_rate": 2.994e-05,
51
+ "loss": 0.502,
52
+ "step": 500
53
+ },
54
+ {
55
+ "epoch": 0.011722779705523774,
56
+ "eval_loss": 0.38173994421958923,
57
+ "eval_runtime": 553.6778,
58
+ "eval_samples_per_second": 136.95,
59
+ "eval_steps_per_second": 34.238,
60
+ "step": 500
61
+ },
62
+ {
63
+ "epoch": 0.014067335646628529,
64
+ "grad_norm": 0.683403730392456,
65
+ "learning_rate": 2.99766978408235e-05,
66
+ "loss": 0.4372,
67
+ "step": 600
68
+ },
69
+ {
70
+ "epoch": 0.016411891587733284,
71
+ "grad_norm": 0.6685835719108582,
72
+ "learning_rate": 2.995316030630178e-05,
73
+ "loss": 0.4075,
74
+ "step": 700
75
+ },
76
+ {
77
+ "epoch": 0.01875644752883804,
78
+ "grad_norm": 0.7494884729385376,
79
+ "learning_rate": 2.9929622771780066e-05,
80
+ "loss": 0.3886,
81
+ "step": 800
82
+ },
83
+ {
84
+ "epoch": 0.021101003469942793,
85
+ "grad_norm": 0.6221954226493835,
86
+ "learning_rate": 2.990608523725835e-05,
87
+ "loss": 0.387,
88
+ "step": 900
89
+ },
90
+ {
91
+ "epoch": 0.023445559411047548,
92
+ "grad_norm": 0.6262496709823608,
93
+ "learning_rate": 2.9882547702736632e-05,
94
+ "loss": 0.3679,
95
+ "step": 1000
96
+ },
97
+ {
98
+ "epoch": 0.023445559411047548,
99
+ "eval_loss": 0.33507269620895386,
100
+ "eval_runtime": 554.2605,
101
+ "eval_samples_per_second": 136.806,
102
+ "eval_steps_per_second": 34.202,
103
+ "step": 1000
104
+ },
105
+ {
106
+ "epoch": 0.025790115352152303,
107
+ "grad_norm": 0.6066267490386963,
108
+ "learning_rate": 2.9859010168214913e-05,
109
+ "loss": 0.3665,
110
+ "step": 1100
111
+ },
112
+ {
113
+ "epoch": 0.028134671293257058,
114
+ "grad_norm": 0.7456773519515991,
115
+ "learning_rate": 2.9835472633693198e-05,
116
+ "loss": 0.3602,
117
+ "step": 1200
118
+ },
119
+ {
120
+ "epoch": 0.030479227234361812,
121
+ "grad_norm": 0.6481399536132812,
122
+ "learning_rate": 2.981193509917148e-05,
123
+ "loss": 0.3511,
124
+ "step": 1300
125
+ },
126
+ {
127
+ "epoch": 0.03282378317546657,
128
+ "grad_norm": 0.6657889485359192,
129
+ "learning_rate": 2.9788397564649763e-05,
130
+ "loss": 0.348,
131
+ "step": 1400
132
+ },
133
+ {
134
+ "epoch": 0.03516833911657132,
135
+ "grad_norm": 0.6899926662445068,
136
+ "learning_rate": 2.9764860030128045e-05,
137
+ "loss": 0.3446,
138
+ "step": 1500
139
+ },
140
+ {
141
+ "epoch": 0.03516833911657132,
142
+ "eval_loss": 0.3230918049812317,
143
+ "eval_runtime": 559.4449,
144
+ "eval_samples_per_second": 135.538,
145
+ "eval_steps_per_second": 33.885,
146
+ "step": 1500
147
+ },
148
+ {
149
+ "epoch": 0.03751289505767608,
150
+ "grad_norm": 0.6252778172492981,
151
+ "learning_rate": 2.974132249560633e-05,
152
+ "loss": 0.341,
153
+ "step": 1600
154
+ },
155
+ {
156
+ "epoch": 0.03985745099878083,
157
+ "grad_norm": 0.5434716939926147,
158
+ "learning_rate": 2.971778496108461e-05,
159
+ "loss": 0.3385,
160
+ "step": 1700
161
+ },
162
+ {
163
+ "epoch": 0.042202006939885586,
164
+ "grad_norm": 0.5847312211990356,
165
+ "learning_rate": 2.969424742656289e-05,
166
+ "loss": 0.3388,
167
+ "step": 1800
168
+ },
169
+ {
170
+ "epoch": 0.04454656288099034,
171
+ "grad_norm": 0.6081641912460327,
172
+ "learning_rate": 2.9670709892041176e-05,
173
+ "loss": 0.3363,
174
+ "step": 1900
175
+ },
176
+ {
177
+ "epoch": 0.046891118822095096,
178
+ "grad_norm": 0.6961779594421387,
179
+ "learning_rate": 2.964717235751946e-05,
180
+ "loss": 0.3322,
181
+ "step": 2000
182
+ },
183
+ {
184
+ "epoch": 0.046891118822095096,
185
+ "eval_loss": 0.3134996294975281,
186
+ "eval_runtime": 560.4988,
187
+ "eval_samples_per_second": 135.283,
188
+ "eval_steps_per_second": 33.822,
189
+ "step": 2000
190
+ },
191
+ {
192
+ "epoch": 0.04923567476319985,
193
+ "grad_norm": 0.6722837090492249,
194
+ "learning_rate": 2.9623634822997742e-05,
195
+ "loss": 0.3356,
196
+ "step": 2100
197
+ },
198
+ {
199
+ "epoch": 0.051580230704304605,
200
+ "grad_norm": 0.6635189056396484,
201
+ "learning_rate": 2.9600097288476023e-05,
202
+ "loss": 0.3334,
203
+ "step": 2200
204
+ },
205
+ {
206
+ "epoch": 0.05392478664540936,
207
+ "grad_norm": 0.751340389251709,
208
+ "learning_rate": 2.9576559753954304e-05,
209
+ "loss": 0.3257,
210
+ "step": 2300
211
+ },
212
+ {
213
+ "epoch": 0.056269342586514115,
214
+ "grad_norm": 0.5838881134986877,
215
+ "learning_rate": 2.955302221943259e-05,
216
+ "loss": 0.3284,
217
+ "step": 2400
218
+ },
219
+ {
220
+ "epoch": 0.05861389852761887,
221
+ "grad_norm": 0.6517124772071838,
222
+ "learning_rate": 2.9529484684910874e-05,
223
+ "loss": 0.328,
224
+ "step": 2500
225
+ },
226
+ {
227
+ "epoch": 0.05861389852761887,
228
+ "eval_loss": 0.3083551824092865,
229
+ "eval_runtime": 561.306,
230
+ "eval_samples_per_second": 135.089,
231
+ "eval_steps_per_second": 33.773,
232
+ "step": 2500
233
+ },
234
+ {
235
+ "epoch": 0.060958454468723625,
236
+ "grad_norm": 0.5870581269264221,
237
+ "learning_rate": 2.9505947150389155e-05,
238
+ "loss": 0.3232,
239
+ "step": 2600
240
+ },
241
+ {
242
+ "epoch": 0.06330301040982837,
243
+ "grad_norm": 0.5278292298316956,
244
+ "learning_rate": 2.9482409615867436e-05,
245
+ "loss": 0.3241,
246
+ "step": 2700
247
+ },
248
+ {
249
+ "epoch": 0.06564756635093313,
250
+ "grad_norm": 0.7702547311782837,
251
+ "learning_rate": 2.945887208134572e-05,
252
+ "loss": 0.323,
253
+ "step": 2800
254
+ },
255
+ {
256
+ "epoch": 0.06799212229203788,
257
+ "grad_norm": 0.6794324517250061,
258
+ "learning_rate": 2.9435334546824002e-05,
259
+ "loss": 0.3218,
260
+ "step": 2900
261
+ },
262
+ {
263
+ "epoch": 0.07033667823314264,
264
+ "grad_norm": 0.798893392086029,
265
+ "learning_rate": 2.9411797012302287e-05,
266
+ "loss": 0.3247,
267
+ "step": 3000
268
+ },
269
+ {
270
+ "epoch": 0.07033667823314264,
271
+ "eval_loss": 0.30541837215423584,
272
+ "eval_runtime": 560.0773,
273
+ "eval_samples_per_second": 135.385,
274
+ "eval_steps_per_second": 33.847,
275
+ "step": 3000
276
+ },
277
+ {
278
+ "epoch": 0.07268123417424739,
279
+ "grad_norm": 0.680193305015564,
280
+ "learning_rate": 2.9388259477780568e-05,
281
+ "loss": 0.3229,
282
+ "step": 3100
283
+ },
284
+ {
285
+ "epoch": 0.07502579011535215,
286
+ "grad_norm": 0.5854464173316956,
287
+ "learning_rate": 2.9364721943258852e-05,
288
+ "loss": 0.3174,
289
+ "step": 3200
290
+ },
291
+ {
292
+ "epoch": 0.0773703460564569,
293
+ "grad_norm": 0.6867486238479614,
294
+ "learning_rate": 2.9341184408737134e-05,
295
+ "loss": 0.3141,
296
+ "step": 3300
297
+ },
298
+ {
299
+ "epoch": 0.07971490199756166,
300
+ "grad_norm": 0.5802149772644043,
301
+ "learning_rate": 2.9317646874215415e-05,
302
+ "loss": 0.3217,
303
+ "step": 3400
304
+ },
305
+ {
306
+ "epoch": 0.08205945793866641,
307
+ "grad_norm": 0.5844931602478027,
308
+ "learning_rate": 2.9294109339693696e-05,
309
+ "loss": 0.3203,
310
+ "step": 3500
311
+ },
312
+ {
313
+ "epoch": 0.08205945793866641,
314
+ "eval_loss": 0.30201342701911926,
315
+ "eval_runtime": 560.3182,
316
+ "eval_samples_per_second": 135.327,
317
+ "eval_steps_per_second": 33.833,
318
+ "step": 3500
319
+ },
320
+ {
321
+ "epoch": 0.08440401387977117,
322
+ "grad_norm": 0.6581853032112122,
323
+ "learning_rate": 2.9270571805171984e-05,
324
+ "loss": 0.3144,
325
+ "step": 3600
326
+ },
327
+ {
328
+ "epoch": 0.08674856982087592,
329
+ "grad_norm": 0.6662478446960449,
330
+ "learning_rate": 2.9247034270650265e-05,
331
+ "loss": 0.3146,
332
+ "step": 3700
333
+ },
334
+ {
335
+ "epoch": 0.08909312576198068,
336
+ "grad_norm": 0.7843517065048218,
337
+ "learning_rate": 2.9223496736128546e-05,
338
+ "loss": 0.3159,
339
+ "step": 3800
340
+ },
341
+ {
342
+ "epoch": 0.09143768170308543,
343
+ "grad_norm": 0.6684930920600891,
344
+ "learning_rate": 2.9199959201606828e-05,
345
+ "loss": 0.3136,
346
+ "step": 3900
347
+ },
348
+ {
349
+ "epoch": 0.09378223764419019,
350
+ "grad_norm": 0.51703941822052,
351
+ "learning_rate": 2.9176421667085112e-05,
352
+ "loss": 0.3133,
353
+ "step": 4000
354
+ },
355
+ {
356
+ "epoch": 0.09378223764419019,
357
+ "eval_loss": 0.2996933162212372,
358
+ "eval_runtime": 562.1924,
359
+ "eval_samples_per_second": 134.876,
360
+ "eval_steps_per_second": 33.72,
361
+ "step": 4000
362
+ },
363
+ {
364
+ "epoch": 0.09612679358529494,
365
+ "grad_norm": 0.7229161858558655,
366
+ "learning_rate": 2.9152884132563397e-05,
367
+ "loss": 0.3107,
368
+ "step": 4100
369
+ },
370
+ {
371
+ "epoch": 0.0984713495263997,
372
+ "grad_norm": 0.6924107074737549,
373
+ "learning_rate": 2.9129346598041678e-05,
374
+ "loss": 0.3131,
375
+ "step": 4200
376
+ },
377
+ {
378
+ "epoch": 0.10081590546750445,
379
+ "grad_norm": 0.7141218185424805,
380
+ "learning_rate": 2.910580906351996e-05,
381
+ "loss": 0.3144,
382
+ "step": 4300
383
+ },
384
+ {
385
+ "epoch": 0.10316046140860921,
386
+ "grad_norm": 0.6682331562042236,
387
+ "learning_rate": 2.9082271528998244e-05,
388
+ "loss": 0.3138,
389
+ "step": 4400
390
+ },
391
+ {
392
+ "epoch": 0.10550501734971396,
393
+ "grad_norm": 0.5962845683097839,
394
+ "learning_rate": 2.9058733994476525e-05,
395
+ "loss": 0.3104,
396
+ "step": 4500
397
+ },
398
+ {
399
+ "epoch": 0.10550501734971396,
400
+ "eval_loss": 0.29778608679771423,
401
+ "eval_runtime": 562.3478,
402
+ "eval_samples_per_second": 134.838,
403
+ "eval_steps_per_second": 33.71,
404
+ "step": 4500
405
+ },
406
+ {
407
+ "epoch": 0.10784957329081872,
408
+ "grad_norm": 0.6476929187774658,
409
+ "learning_rate": 2.903519645995481e-05,
410
+ "loss": 0.308,
411
+ "step": 4600
412
+ },
413
+ {
414
+ "epoch": 0.11019412923192347,
415
+ "grad_norm": 0.6191292405128479,
416
+ "learning_rate": 2.901165892543309e-05,
417
+ "loss": 0.3095,
418
+ "step": 4700
419
+ },
420
+ {
421
+ "epoch": 0.11253868517302823,
422
+ "grad_norm": 0.5744597911834717,
423
+ "learning_rate": 2.8988121390911375e-05,
424
+ "loss": 0.3077,
425
+ "step": 4800
426
+ },
427
+ {
428
+ "epoch": 0.11488324111413298,
429
+ "grad_norm": 0.7545962929725647,
430
+ "learning_rate": 2.8964583856389657e-05,
431
+ "loss": 0.3084,
432
+ "step": 4900
433
+ },
434
+ {
435
+ "epoch": 0.11722779705523774,
436
+ "grad_norm": 0.6554388999938965,
437
+ "learning_rate": 2.8941046321867938e-05,
438
+ "loss": 0.309,
439
+ "step": 5000
440
+ },
441
+ {
442
+ "epoch": 0.11722779705523774,
443
+ "eval_loss": 0.2962198555469513,
444
+ "eval_runtime": 561.1396,
445
+ "eval_samples_per_second": 135.129,
446
+ "eval_steps_per_second": 33.783,
447
+ "step": 5000
448
+ },
449
+ {
450
+ "epoch": 0.11957235299634249,
451
+ "grad_norm": 0.613491952419281,
452
+ "learning_rate": 2.891750878734622e-05,
453
+ "loss": 0.3057,
454
+ "step": 5100
455
+ },
456
+ {
457
+ "epoch": 0.12191690893744725,
458
+ "grad_norm": 0.5974335074424744,
459
+ "learning_rate": 2.8893971252824507e-05,
460
+ "loss": 0.3064,
461
+ "step": 5200
462
+ },
463
+ {
464
+ "epoch": 0.124261464878552,
465
+ "grad_norm": 0.6582714319229126,
466
+ "learning_rate": 2.887043371830279e-05,
467
+ "loss": 0.305,
468
+ "step": 5300
469
+ },
470
+ {
471
+ "epoch": 0.12660602081965674,
472
+ "grad_norm": 0.520508348941803,
473
+ "learning_rate": 2.884689618378107e-05,
474
+ "loss": 0.3023,
475
+ "step": 5400
476
+ },
477
+ {
478
+ "epoch": 0.12895057676076152,
479
+ "grad_norm": 0.6541963815689087,
480
+ "learning_rate": 2.882335864925935e-05,
481
+ "loss": 0.3086,
482
+ "step": 5500
483
+ },
484
+ {
485
+ "epoch": 0.12895057676076152,
486
+ "eval_loss": 0.2944982349872589,
487
+ "eval_runtime": 561.0929,
488
+ "eval_samples_per_second": 135.14,
489
+ "eval_steps_per_second": 33.786,
490
+ "step": 5500
491
+ },
492
+ {
493
+ "epoch": 0.13129513270186627,
494
+ "grad_norm": 0.6329942345619202,
495
+ "learning_rate": 2.8799821114737635e-05,
496
+ "loss": 0.3057,
497
+ "step": 5600
498
+ },
499
+ {
500
+ "epoch": 0.13363968864297102,
501
+ "grad_norm": 0.7279817461967468,
502
+ "learning_rate": 2.877628358021592e-05,
503
+ "loss": 0.3064,
504
+ "step": 5700
505
+ },
506
+ {
507
+ "epoch": 0.13598424458407576,
508
+ "grad_norm": 0.5646392107009888,
509
+ "learning_rate": 2.87527460456942e-05,
510
+ "loss": 0.3059,
511
+ "step": 5800
512
+ },
513
+ {
514
+ "epoch": 0.13832880052518054,
515
+ "grad_norm": 0.639140248298645,
516
+ "learning_rate": 2.8729208511172482e-05,
517
+ "loss": 0.3049,
518
+ "step": 5900
519
+ },
520
+ {
521
+ "epoch": 0.1406733564662853,
522
+ "grad_norm": 0.5572499632835388,
523
+ "learning_rate": 2.8705670976650767e-05,
524
+ "loss": 0.3066,
525
+ "step": 6000
526
+ },
527
+ {
528
+ "epoch": 0.1406733564662853,
529
+ "eval_loss": 0.29302480816841125,
530
+ "eval_runtime": 561.3497,
531
+ "eval_samples_per_second": 135.078,
532
+ "eval_steps_per_second": 33.77,
533
+ "step": 6000
534
+ },
535
+ {
536
+ "epoch": 0.14301791240739004,
537
+ "grad_norm": 0.6419617533683777,
538
+ "learning_rate": 2.8682133442129048e-05,
539
+ "loss": 0.3016,
540
+ "step": 6100
541
+ },
542
+ {
543
+ "epoch": 0.14536246834849478,
544
+ "grad_norm": 0.5800477862358093,
545
+ "learning_rate": 2.8658595907607333e-05,
546
+ "loss": 0.3022,
547
+ "step": 6200
548
+ },
549
+ {
550
+ "epoch": 0.14770702428959956,
551
+ "grad_norm": 0.5249703526496887,
552
+ "learning_rate": 2.8635058373085614e-05,
553
+ "loss": 0.3022,
554
+ "step": 6300
555
+ },
556
+ {
557
+ "epoch": 0.1500515802307043,
558
+ "grad_norm": 0.6495929956436157,
559
+ "learning_rate": 2.86115208385639e-05,
560
+ "loss": 0.3037,
561
+ "step": 6400
562
+ },
563
+ {
564
+ "epoch": 0.15239613617180905,
565
+ "grad_norm": 0.626995325088501,
566
+ "learning_rate": 2.858798330404218e-05,
567
+ "loss": 0.3033,
568
+ "step": 6500
569
+ },
570
+ {
571
+ "epoch": 0.15239613617180905,
572
+ "eval_loss": 0.2912672758102417,
573
+ "eval_runtime": 560.0877,
574
+ "eval_samples_per_second": 135.382,
575
+ "eval_steps_per_second": 33.846,
576
+ "step": 6500
577
+ },
578
+ {
579
+ "epoch": 0.1547406921129138,
580
+ "grad_norm": 0.6745596528053284,
581
+ "learning_rate": 2.856444576952046e-05,
582
+ "loss": 0.2999,
583
+ "step": 6600
584
+ },
585
+ {
586
+ "epoch": 0.15708524805401858,
587
+ "grad_norm": 0.6391417980194092,
588
+ "learning_rate": 2.8540908234998742e-05,
589
+ "loss": 0.3049,
590
+ "step": 6700
591
+ },
592
+ {
593
+ "epoch": 0.15942980399512333,
594
+ "grad_norm": 0.8039213418960571,
595
+ "learning_rate": 2.851737070047703e-05,
596
+ "loss": 0.3012,
597
+ "step": 6800
598
+ },
599
+ {
600
+ "epoch": 0.16177435993622807,
601
+ "grad_norm": 0.6973159909248352,
602
+ "learning_rate": 2.849383316595531e-05,
603
+ "loss": 0.3019,
604
+ "step": 6900
605
+ },
606
+ {
607
+ "epoch": 0.16411891587733282,
608
+ "grad_norm": 0.6347749829292297,
609
+ "learning_rate": 2.8470295631433593e-05,
610
+ "loss": 0.3022,
611
+ "step": 7000
612
+ },
613
+ {
614
+ "epoch": 0.16411891587733282,
615
+ "eval_loss": 0.29215002059936523,
616
+ "eval_runtime": 560.1099,
617
+ "eval_samples_per_second": 135.377,
618
+ "eval_steps_per_second": 33.845,
619
+ "step": 7000
620
+ },
621
+ {
622
+ "epoch": 0.1664634718184376,
623
+ "grad_norm": 0.6030504703521729,
624
+ "learning_rate": 2.8446758096911874e-05,
625
+ "loss": 0.3045,
626
+ "step": 7100
627
+ },
628
+ {
629
+ "epoch": 0.16880802775954235,
630
+ "grad_norm": 0.7266963124275208,
631
+ "learning_rate": 2.842322056239016e-05,
632
+ "loss": 0.299,
633
+ "step": 7200
634
+ },
635
+ {
636
+ "epoch": 0.1711525837006471,
637
+ "grad_norm": 0.5945442914962769,
638
+ "learning_rate": 2.8399683027868443e-05,
639
+ "loss": 0.2994,
640
+ "step": 7300
641
+ },
642
+ {
643
+ "epoch": 0.17349713964175184,
644
+ "grad_norm": 0.8690565228462219,
645
+ "learning_rate": 2.8376145493346724e-05,
646
+ "loss": 0.3036,
647
+ "step": 7400
648
+ },
649
+ {
650
+ "epoch": 0.17584169558285662,
651
+ "grad_norm": 0.6460816264152527,
652
+ "learning_rate": 2.8352607958825006e-05,
653
+ "loss": 0.2988,
654
+ "step": 7500
655
+ },
656
+ {
657
+ "epoch": 0.17584169558285662,
658
+ "eval_loss": 0.2912307679653168,
659
+ "eval_runtime": 561.9772,
660
+ "eval_samples_per_second": 134.927,
661
+ "eval_steps_per_second": 33.733,
662
+ "step": 7500
663
+ },
664
+ {
665
+ "epoch": 0.17818625152396136,
666
+ "grad_norm": 0.646554172039032,
667
+ "learning_rate": 2.832907042430329e-05,
668
+ "loss": 0.3014,
669
+ "step": 7600
670
+ },
671
+ {
672
+ "epoch": 0.1805308074650661,
673
+ "grad_norm": 0.6531568765640259,
674
+ "learning_rate": 2.830553288978157e-05,
675
+ "loss": 0.2994,
676
+ "step": 7700
677
+ },
678
+ {
679
+ "epoch": 0.18287536340617086,
680
+ "grad_norm": 0.6899993419647217,
681
+ "learning_rate": 2.8281995355259853e-05,
682
+ "loss": 0.3015,
683
+ "step": 7800
684
+ },
685
+ {
686
+ "epoch": 0.18521991934727564,
687
+ "grad_norm": 0.5150295495986938,
688
+ "learning_rate": 2.825845782073814e-05,
689
+ "loss": 0.2997,
690
+ "step": 7900
691
+ },
692
+ {
693
+ "epoch": 0.18756447528838038,
694
+ "grad_norm": 0.7084159255027771,
695
+ "learning_rate": 2.8234920286216422e-05,
696
+ "loss": 0.2993,
697
+ "step": 8000
698
+ },
699
+ {
700
+ "epoch": 0.18756447528838038,
701
+ "eval_loss": 0.29071754217147827,
702
+ "eval_runtime": 560.185,
703
+ "eval_samples_per_second": 135.359,
704
+ "eval_steps_per_second": 33.841,
705
+ "step": 8000
706
+ }
707
+ ],
708
+ "logging_steps": 100,
709
+ "max_steps": 127956,
710
+ "num_input_tokens_seen": 0,
711
+ "num_train_epochs": 3,
712
+ "save_steps": 500,
713
+ "stateful_callbacks": {
714
+ "EarlyStoppingCallback": {
715
+ "args": {
716
+ "early_stopping_patience": 3,
717
+ "early_stopping_threshold": 0.001
718
+ },
719
+ "attributes": {
720
+ "early_stopping_patience_counter": 3
721
+ }
722
+ },
723
+ "TrainerControl": {
724
+ "args": {
725
+ "should_epoch_stop": false,
726
+ "should_evaluate": false,
727
+ "should_log": false,
728
+ "should_save": true,
729
+ "should_training_stop": true
730
+ },
731
+ "attributes": {}
732
+ }
733
+ },
734
+ "total_flos": 2.7053294960787456e+16,
735
+ "train_batch_size": 4,
736
+ "trial_name": null,
737
+ "trial_params": null
738
+ }
checkpoint-8000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f4782bd16b2095bcd48ed561cca0b58ff457efc18a2d0171cfcd8019f2a410
3
+ size 5304
checkpoint-8000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f4782bd16b2095bcd48ed561cca0b58ff457efc18a2d0171cfcd8019f2a410
3
+ size 5304